# Multi-intention Inverse Q-learning for Interpretable Behavior Representation

arXiv: https://arxiv.org/abs/2311.13870 · HTML: https://mlsanity.com/paper/2311.13870/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Inverse reinforcement learning, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 8 of its 44 references that are in the map.
- First posted on arXiv 23 Nov 2023.

## Placed in

- Offline RL and imitation learning from data / [Inverse reinforcement learning](https://mlsanity.com/offlinerl/inverse-reinforcement-learning/)

## Builds on (most cited first, 8 of 8)

- [A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progress](https://mlsanity.com/paper/1806.06877/) (2018)
- [Scalable Bayesian Inverse Reinforcement Learning](https://mlsanity.com/paper/2102.06483/) (2021)
- [Graph Inverse Reinforcement Learning from Diverse Videos](https://mlsanity.com/paper/2207.14299/) (2022)
- [Multi-task Maximum Entropy Inverse Reinforcement Learning](https://mlsanity.com/paper/1805.08882/) (2018)
- [Deep Inverse Q-learning with Constraints](https://mlsanity.com/paper/2008.01712/) (2020)
- [Inverse Rational Control with Partially Observable Continuous Nonlinear Dynamics](https://mlsanity.com/paper/1908.04696/) (2019)
- [Option-Aware Adversarial Inverse Reinforcement Learning for Robotic Control](https://mlsanity.com/paper/2210.01969/) (2022)
- [Deep Adaptive Multi-Intention Inverse Reinforcement Learning](https://mlsanity.com/paper/2107.06692/) (2021)

## Built on by (most cited first, 9 of 9)

- [Inverse Reinforcement Learning with Switching Rewards and History Dependency for Characterizing Animal Behaviors](https://mlsanity.com/paper/2501.12633/) (2025)
- [Learning Reward Machines from Partially Observed Policies](https://mlsanity.com/paper/2502.03762/) (2025)
- [Solving Inverse Problem for Multi-armed Bandits via Convex Optimization](https://mlsanity.com/paper/2501.18945/) (2025)
- [Multi-convex Programming for Discrete Latent Factor Models Prototyping](https://mlsanity.com/paper/2504.01431/) (2025)
- [Learning Task-Agnostic Motifs to Capture the Continuous Nature of Animal Behavior](https://mlsanity.com/paper/2506.15190/) (2025)
- [Inverse Reinforcement Learning via Convex Optimization](https://mlsanity.com/paper/2501.15957/) (2025)
- [Fitting Reinforcement Learning Model to Behavioral Data under Bandits](https://mlsanity.com/paper/2511.04454/) (2025)
- [Probabilistic Recurrent Intention Switching Model](https://mlsanity.com/paper/2605.26998/) (2026)
- [Exploratory Experience Shapes the Geometry of Predictive Representations](https://mlsanity.com/paper/2605.27929/) (2026)

## Abstract (arXiv)

In advancing the understanding of natural decision-making processes, inverse reinforcement learning (IRL) methods have proven instrumental in reconstructing animal's intentions underlying complex behaviors. Given the recent development of a continuous-time multi-intention IRL framework, there has been persistent inquiry into inferring discrete time-varying rewards with IRL. To address this challenge, we introduce the class of hierarchical inverse Q-learning (HIQL) algorithms. Through an unsupervised learning process, HIQL divides expert trajectories into multiple intention segments, and solves the IRL problem independently for each. Applying HIQL to simulated experiments and several real animal behavior datasets, our approach outperforms current benchmarks in behavior prediction and produces interpretable reward functions. Our results suggest that the intention transition dynamics underlying complex decision-making behavior is better modeled by a step function instead of a smoothly varying function. This advancement holds promise for neuroscience and cognitive science, contributing to a deeper understanding of decision-making and uncovering underlying brain mechanisms.